Papers by David Contreras Vazquez
Proceedings Cvpr Ieee Computer Society Conference on Computer Vision and Pattern Recognition Ieee Computer Society Conference on Computer Vision and Pattern Recognition, 2010
Bookmarks Related papers MentionsView impact
ABSTRACT Pedestrian detection is of paramount interest for many applications, e.g. Advanced Drive... more ABSTRACT Pedestrian detection is of paramount interest for many applications, e.g. Advanced Driver Assistance Systems, Intelligent Video Surveillance and Multimedia systems. Most promising pedestrian detectors rely on appearance-based classifiers trained with annotated data. However, the required annotation step represents an intensive and subjective task for humans, what makes worth to minimize their intervention in this process by using computational tools like realistic virtual worlds. The reason to use these kind of tools relies in the fact that they allow the automatic generation of precise and rich annotations of visual information. Nevertheless, the use of this kind of data comes with the following question: can a pedestrian appearance model learnt with virtual-world data work successfully for pedestrian detection in real-world scenarios?. To answer this question, we conduct different experiments that suggest a positive answer. However, the pedestrian classifiers trained with virtual-world data can suffer the so called dataset shift problem as real-world based classifiers does. Accordingly, we have designed different domain adaptation techniques to face this problem, all of them integrated in a same framework (V-AYLA). We have explored different methods to train a domain adapted pedestrian classifiers by collecting a few pedestrian samples from the target domain (real world) and combining them with many samples of the source domain (virtual world). The extensive experiments we present show that pedestrian detectors developed within the V-AYLA framework do achieve domain adaptation. Ideally, we would like to adapt our system without any human intervention. Therefore, as a first proof of concept we also propose an unsupervised domain adaptation technique that avoids human intervention during the adaptation process. To the best of our knowledge, this Thesis work is the first demonstrating adaptation of virtual and real worlds for developing an object detector. Last but not least, we also assessed a different strategy to avoid the dataset shift that consists in collecting real-world samples and retrain with them in such a way that no bounding boxes of real-world pedestrians have to be provided. We show that the generated classifier is competitive with respect to the counterpart trained with samples collected by manually annotating pedestrian bounding boxes. The results presented on this Thesis not only end with a proposal for adapting a virtual-world pedestrian detector to the real world, but also it goes further by pointing out a new methodology that would allow the system to adapt to different situations, which we hope will provide the foundations for future research in this unexplored area.
Bookmarks Related papers MentionsView impact
Biochemistry Usa, 1979
... CAMPLZANO, VAZQUEZ, AND MODOLELL ... Moreover, the ternary complex containing GDP is stabiliz... more ... CAMPLZANO, VAZQUEZ, AND MODOLELL ... Moreover, the ternary complex containing GDP is stabilized by fusidic acid and it is usually studied in the form of a quaternary complex containing one molecule of this antibiotic (Bodley et al., 1970; Willie et al., 1975). ...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Sensors (Basel, Switzerland), Jan 4, 2016
Despite all the significant advances in pedestrian detection brought by computer vision for drivi... more Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and nighttime. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images; (b) just infrared images; and (c) both of them. In order to obtain results for the last item, we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset that we...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Image based human detection is of great interest due to its potential applications. However, even... more Image based human detection is of great interest due to its potential applications. However, even detecting non-occluded standing humans remains challenging [4]. This is not surprising due to the large variety of backgrounds (scenarios, illumination) in which ...
Bookmarks Related papers MentionsView impact
Journal of Biological Chemistry, Jan 25, 1973
Bookmarks Related papers MentionsView impact
Salud Mental, 2000
Bookmarks Related papers MentionsView impact
Proceedings of the 21st International Conference on Pattern Recognition, 2012
Bookmarks Related papers MentionsView impact
Journal of Biological Chemistry, Dec 25, 1973
Bookmarks Related papers MentionsView impact
Actas Dermo Sifiliograficas, 1990
... Auteur(s) / Author(s). RUFIN VILLAOSLADA J. ; PEREDA HERNANDEZ J. ; ABBAD ASENSIO LE ; DRONDA... more ... Auteur(s) / Author(s). RUFIN VILLAOSLADA J. ; PEREDA HERNANDEZ J. ; ABBAD ASENSIO LE ; DRONDA NUNEZ F. ; MARTINEZ MARTINEZ P. ; DE AGUSTIN VAZQUEZ D. ; Affiliation(s) du ou des auteurs / Author(s) Affiliation(s). Hosp. naval Miditerráneo, serv. ...
Bookmarks Related papers MentionsView impact
2015 Ieee Winter Conference on Applications of Computer Vision, 2015
Bookmarks Related papers MentionsView impact
Pnas, 1973
N-Acetyl-Phe-tRNA, nonenzymically bound to the acceptor site of Escherichia coli ribosomes, readi... more N-Acetyl-Phe-tRNA, nonenzymically bound to the acceptor site of Escherichia coli ribosomes, readily undergoes translocation in the presence of elongation factor (EF)-G and GTP. The translocated N-acetyl-Phe-tRNA, bound to the ribosomal donor site, prevents further interaction of EF-G with the ribosome, for it inhibits the GTP hydrolysis that takes place in the presence of EF-G and ribosomes and it decreases the
Bookmarks Related papers MentionsView impact
International Journal of Computer Vision, 2016
Bookmarks Related papers MentionsView impact
ABSTRACT
Bookmarks Related papers MentionsView impact
ABSTRACT
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Pedestrian accidents are one of the leading preventable causes of death. In order to reduce the n... more Pedestrian accidents are one of the leading preventable causes of death. In order to reduce the number of accidents, in the last decade the pedestrian protection systems have been introduced, a special type of advanced driver assistance systems, in witch an on-board camera explores the road ahead for possible collisions with pedestrians in order to warn the driver or perform braking actions. As a result of the variability of the appearance, pose and size, pedestrian detection is a very challenging task. So many techniques, models and features have been proposed to solve the problem. As the appearance of pedestrians varies significantly as a function of distance, a system based on multiple classifiers specialized on different depths is likely to improve the overall performance with respect to a typical system based on a general detector. Accordingly, the main aim of this work is to explore the effect of the distance in pedestrian detection. We have evaluated three pedestrian detector...
Bookmarks Related papers MentionsView impact
Uploads
Papers by David Contreras Vazquez